Python抓取HTML网页并以PDF保存

Posted 2020-09-06 胡宝全

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Python抓取HTML网页并以PDF保存相关的知识，希望对你有一定的参考价值。

一、前言

今天介绍将HTML网页抓取下来，然后以PDF保存，废话不多说直接进入教程。

今天的例子以廖雪峰老师的Python教程网站为例：http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000

二、准备工作

PyPDF2的安装使用（用来合并PDF）：

PyPDF2版本：1.25.1

https://pypi.python.org/pypi/PyPDF2/1.25.1

或

https://github.com/mstamy2/PyPDF2

安装：

pip install PyPDF2

使用示例：

from PyPDF2 import PdfFileMerger

merger = PdfFileMerger()

input1 = open("hql_1_20.pdf", "rb")

input2 = open("hql_21_40.pdf", "rb")

merger.append(input1)

merger.append(input2)

# Write to an output PDF document

output = open("hql_all.pdf", "wb")

merger.write(output)

requests、beautifulsoup 是爬虫两大神器，reuqests 用于网络请求，beautifusoup 用于操作 html 数据。有了这两把梭子，干起活来利索。scrapy 这样的爬虫框架我们就不用了，这样的小程序派上它有点杀鸡用牛刀的意思。此外，既然是把 html 文件转为 pdf，那么也要有相应的库支持， wkhtmltopdf 就是一个非常的工具，它可以用适用于多平台的 html 到 pdf 的转换，pdfkit 是 wkhtmltopdf 的Python封装包。首先安装好下面的依赖包
```
pip install requests
pip install beautifulsoup4
pip install pdfkit
```
安装 wkhtmltopdf

Windows平台直接在 http://wkhtmltopdf.org/downloads.html 下载稳定版的 wkhtmltopdf 进行安装，安装完成之后把该程序的执行路径加入到系统环境 $PATH 变量中，否则 pdfkit 找不到 wkhtmltopdf 就出现错误 “No wkhtmltopdf executable found”。Ubuntu 和 CentOS 可以直接用命令行进行安装
```
$ sudo apt-get install wkhtmltopdf  # ubuntu
$ sudo yum intsall wkhtmltopdf      # centos
```

三、数据准备

1.获取每篇文章的url

def get_url_list():
    """
    获取所有URL目录列表
    :return:
    """
    response = requests.get("http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000")
    soup = BeautifulSoup(response.content, "html.parser")
    menu_tag = soup.find_all(class_="uk-nav uk-nav-side")[1]
    urls = []
    for li in menu_tag.find_all("li"):
        url = "http://www.liaoxuefeng.com" + li.a.get(‘href‘)
        urls.append(url)
    return urls

2.通过文章url用模板保存每篇文章的HTML文件

html模板：

html_template = """
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
</head>
<body>
{content}
</body>
</html>

"""

进行保存：

def parse_url_to_html(url, name):
    """
    解析URL，返回HTML内容
    :param url:解析的url
    :param name: 保存的html文件名
    :return: html
    """
    try:
        response = requests.get(url)
        soup = BeautifulSoup(response.content, ‘html.parser‘)
        # 正文
        body = soup.find_all(class_="x-wiki-content")[0]
        # 标题
        title = soup.find(‘h4‘).get_text()

        # 标题加入到正文的最前面，居中显示
        center_tag = soup.new_tag("center")
        title_tag = soup.new_tag(‘h1‘)
        title_tag.string = title
        center_tag.insert(1, title_tag)
        body.insert(1, center_tag)
        html = str(body)
        # body中的img标签的src相对路径的改成绝对路径
        pattern = "(<img .*?src=\")(.*?)(\")"

        def func(m):
            if not m.group(3).startswith("http"):
                rtn = m.group(1) + "http://www.liaoxuefeng.com" + m.group(2) + m.group(3)
                return rtn
            else:
                return m.group(1)+m.group(2)+m.group(3)
        html = re.compile(pattern).sub(func, html)
        html = html_template.format(content=html)
        html = html.encode("utf-8")
        with open(name, ‘wb‘) as f:
            f.write(html)
        return name

    except Exception as e:

        logging.error("解析错误", exc_info=True)

3.把html转换成pdf

def save_pdf(htmls, file_name):
    """
    把所有html文件保存到pdf文件
    :param htmls:  html文件列表
    :param file_name: pdf文件名
    :return:
    """
    options = {
        ‘page-size‘: ‘Letter‘,
        ‘margin-top‘: ‘0.75in‘,
        ‘margin-right‘: ‘0.75in‘,
        ‘margin-bottom‘: ‘0.75in‘,
        ‘margin-left‘: ‘0.75in‘,
        ‘encoding‘: "UTF-8",
        ‘custom-header‘: [
            (‘Accept-Encoding‘, ‘gzip‘)
        ],
        ‘cookie‘: [
            (‘cookie-name1‘, ‘cookie-value1‘),
            (‘cookie-name2‘, ‘cookie-value2‘),
        ],
        ‘outline-depth‘: 10,
    }
    pdfkit.from_file(htmls, file_name, options=options)

4.把转换好的单个PDF合并为一个PDF

    merger = PdfFileMerger()
    for pdf in pdfs:
       merger.append(open(pdf,‘rb‘))
       print u"合并完成第"+str(i)+‘个pdf‘+pdf

完整源码：

# coding=utf-8
import os
import re
import time
import logging
import pdfkit
import requests
from bs4 import BeautifulSoup
from PyPDF2 import PdfFileMerger

html_template = """
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
</head>
<body>
{content}
</body>
</html>

"""


def parse_url_to_html(url, name):
    """
    解析URL，返回HTML内容
    :param url:解析的url
    :param name: 保存的html文件名
    :return: html
    """
    try:
        response = requests.get(url)
        soup = BeautifulSoup(response.content, ‘html.parser‘)
        # 正文
        body = soup.find_all(class_="x-wiki-content")[0]
        # 标题
        title = soup.find(‘h4‘).get_text()

        # 标题加入到正文的最前面，居中显示
        center_tag = soup.new_tag("center")
        title_tag = soup.new_tag(‘h1‘)
        title_tag.string = title
        center_tag.insert(1, title_tag)
        body.insert(1, center_tag)
        html = str(body)
        # body中的img标签的src相对路径的改成绝对路径
        pattern = "(<img .*?src=\")(.*?)(\")"

        def func(m):
            if not m.group(3).startswith("http"):
                rtn = m.group(1) + "http://www.liaoxuefeng.com" + m.group(2) + m.group(3)
                return rtn
            else:
                return m.group(1)+m.group(2)+m.group(3)
        html = re.compile(pattern).sub(func, html)
        html = html_template.format(content=html)
        html = html.encode("utf-8")
        with open(name, ‘wb‘) as f:
            f.write(html)
        return name

    except Exception as e:

        logging.error("解析错误", exc_info=True)


def get_url_list():
    """
    获取所有URL目录列表
    :return:
    """
    response = requests.get("http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000")
    soup = BeautifulSoup(response.content, "html.parser")
    menu_tag = soup.find_all(class_="uk-nav uk-nav-side")[1]
    urls = []
    for li in menu_tag.find_all("li"):
        url = "http://www.liaoxuefeng.com" + li.a.get(‘href‘)
        urls.append(url)
    return urls


def save_pdf(htmls, file_name):
    """
    把所有html文件保存到pdf文件
    :param htmls:  html文件列表
    :param file_name: pdf文件名
    :return:
    """
    options = {
        ‘page-size‘: ‘Letter‘,
        ‘margin-top‘: ‘0.75in‘,
        ‘margin-right‘: ‘0.75in‘,
        ‘margin-bottom‘: ‘0.75in‘,
        ‘margin-left‘: ‘0.75in‘,
        ‘encoding‘: "UTF-8",
        ‘custom-header‘: [
            (‘Accept-Encoding‘, ‘gzip‘)
        ],
        ‘cookie‘: [
            (‘cookie-name1‘, ‘cookie-value1‘),
            (‘cookie-name2‘, ‘cookie-value2‘),
        ],
        ‘outline-depth‘: 10,
    }
    pdfkit.from_file(htmls, file_name, options=options)


def main():
    start = time.time()
    file_name = u"liaoxuefeng_Python3_tutorial"
    urls = get_url_list()
    for index, url in enumerate(urls):
      parse_url_to_html(url, str(index) + ".html")
    htmls =[]
    pdfs =[]
    for i in range(0,124):
        htmls.append(str(i)+‘.html‘)
        pdfs.append(file_name+str(i)+‘.pdf‘)

        save_pdf(str(i)+‘.html‘, file_name+str(i)+‘.pdf‘)

        print u"转换完成第"+str(i)+‘个html‘

    merger = PdfFileMerger()
    for pdf in pdfs:
       merger.append(open(pdf,‘rb‘))
       print u"合并完成第"+str(i)+‘个pdf‘+pdf

    output = open(u"廖雪峰Python_all.pdf", "wb")
    merger.write(output)

    print u"输出PDF成功！"

    for html in htmls:
        os.remove(html)
        print u"删除临时文件"+html

    for pdf in pdfs:
        os.remove(pdf)
        print u"删除临时文件"+pdf

    total_time = time.time() - start
    print(u"总共耗时：%f 秒" % total_time)


if __name__ == ‘__main__‘:
    main()